Push PPO agent to the Hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -110.03 +/- 79.03
+      value: -104.38 +/- 18.56
       name: mean_reward
       verified: false
 ---
@@ -36,7 +36,7 @@ This is a trained model of a PPO agent playing LunarLander-v2.
 'wandb_entity': None
 'capture_video': True
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 8
 'num_steps': 2048

logs/events.out.tfevents.1754231574.43abc99fdb1e.36011.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f40fa2feb6713ed153490d6a8c8895f3d9fe2956db32aa9fadcf35cef870b4d
+size 32155

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d836cc449c075a359d7a0a06cdc6a7369eb119f4efe5098ae148b01ce1a71da5
+oid sha256:4da2c051c967b8bc1f3b9cf9b82fa25ab17d5e093e3ea7d71e8ee8f386a63643
 size 147602

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -110.02536891474179, "std_reward": 79.02843538923116, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-03T14:31:08.729530"}
+{"env_id": "LunarLander-v2", "mean_reward": -104.38407488237135, "std_reward": 18.561551809781786, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-03T15:05:55.637642"}